/PaperRead

📒Record some paper read notes

🤧Some Paper Read By @gunjianpan

This is a repository like 'douban' personal home page in AI field.

❱❱❱❱❱❱❱ ❱❱❱❱❱❱ ❱❱❱❱❱ ❱❱❱❱ ❱❱❱❱ ❱❱❱ ❱❱ ❱

Categories

NLP

NER

Read Public Conference Title HighLight Code Other
191220 190926 ICLR 2020 WKLM add KB in pretrain - -
191113 191110 - TENER improve Transformer in NER - -
191006 190926 - CRF-VAEs VAE in NER - Unlabeled
191006 190925 CONLL 2019 UnifiedNETagger Multi-Corpus NewBioNer Unlabeled
191020 190712 AAAI 2019 GRN +Long-term->CNN GRN -
191220 190327 EMNLP 2019 capitalized capitalized in ner and pos - -

Nested NER

Read Public Conference Title HighLight Code Other
191101 191028 - MRCNER QA gen + Nested QA - -
190916 190910 EMNLP 2019 DyGIE++ Bertology dygiepp -
190919 190905 - Second Best CRF Recursive CRF secondbest optime cost
190912 190903 EMNLP 2019 Combining Spans into Entities Neural Net->CRF disco_em19 Two stage
190920 190824 - Query-based NER ->QA - usePriorInfo
190812 190804 ACL 2019 Linearization Nest NER label -> CONLL-like - Seq2seq
190703 190630 ACL 2019 Merge and label Two-stage mergeLabel threshold
190703 190620 ACL 2019 Multi-Grained NER Two-stage MGNER centerSearch
190707 190405 NAACL 2019 DyGIE Dynamic span graph DyGIE IE Framework

Relation Extraction

Read Public Conference Title HighLight Code Other
191216 191128 AAAI 2020 Inducing Relation Induing Realtion using cloze - -
191128 190607 ACL 2019 Matching the Blanks How to use BERT in relation link BERTem -

Summarization

Read Public Conference Title HighLight Code Other
181212 170725 ICML 2017 ConvS2S CNN semantic fairseq notes

Adversarial

Read Public Conference Title HighLight Code Other
190911 190829 EMNLP 2019 Universal Adversarial Triggers Adversarial-NLP universal-triggers blog

Common Sense

Read Public Conference Title HighLight Code Other
191218 190904 EMNLP 2019 KagNet Commonsense via KB + Pretrain KagNet -

Bertology

Read Public Conference Title HighLight Code Other
191112 191029 - BART Auto-Encode + Auto-Regressive - -
191024 191024 - T5 Decathlon T5 C4
191113 190926 ICLR 2020 ELECTRA GAN -> difficult MASK - -
190928 190926 ICLR 2020 ALBert ReduceParams - -
190801 190508 - UniLM three Mask unilm -

Distilled

Read Public Conference Title HighLight Code Other
191228 190926 ICLR 2020 DEFINE reduce embed size + residual - -
191002 190926 - TinyBert new tew-stage - -

Bert Distilled

Read Public Conference Title HighLight Code Other
191018 191002 NIPS 2019 DistillBert support device transformers -
191002 190926 - TinyBert new tew-stage - -

Bert Probe

Read Public Conference Title HighLight Code Other
191216 190904 EMNLP 2019 LM as KB? Bert in Relation Extraction [LAMA][]10054 -
191014 190515 ACL 2019 Bert Rediscover probe bert layer - -

Bert DownStream

Read Public Conference Title HighLight Code Other
191020 190827 EMNLP 2019 Sentence Bert Bert in STS sentence-transformers -

Parallelism

Read Public Conference Title HighLight Code Other
191017 191005 - Megatron-LM parallelism & little code change megatron-LM blog

NLG

Read Public Conference Title HighLight Code Other
191005 191001 ICLR 2020 BertScore auto evaluation use bert bertScore -
190926 190926 - CTRL controllable generation ctrl -
191010 190812 - UnLikelihood unLikelihood -

Text Style Transfer

Read Public Conference Title HighLight Code Other
191006 190925 EMNLP 2019 CrossProject Latent Space Project CrossProject -

Discourse Parsing

Read Public Conference Title HighLight Code Other
191111 191030 EMNLP 2019 Predict DS using sentiment using sentiment generate DP dataSet - -

Chinese

Read Public Conference Title HighLight Code Other
191013 190906 - NeZha chinese bert - -

ML

Metric Learning

Read Public Conference Title HighLight Code Other
190829 190525 NIPS 2019 Constellation Loss Multiclass n + Triple constellation_loss -
191007 170406 CVPR 2017 Quadruplet Loss two margin - -
190827 160601 CVPR 2016 Multi-class N-pair Loss multi negative sample - -
190827 150617 CVPR 2015 Triplet Loss Triple - -

Transformer

Read Public Conference Title HighLight Code Other
191229 191127 - SHA-RNN RNN + Att sha-rnn -
191028 191022 ICLR 2020 Depth-adaptive Transformer depth adaptive - -
190929 190926 - LayerNorm Transformer improve warm-up - -
190716 190710 - Large Memory Layer KeyValue search XLM twitter
190718 190624 NIPS 2019 Tensorized Transformer decompose + param share - -
190908 190606 - Macaron Net Strange-Macaron - note
190718 190519 ACL 2019 Adaptive Att span adapting span adaptiveSpan -
191118 190228 NAACL 2019 Star Transformer FFN -> Star Arch fastNLP -
190719 180710 ICLR 2019 Universal Transformer Recurrent + ACT UT slider

Attention

Read Public Conference Title HighLight Code Other
190819 190607 ACL 2019 Analysis Multi-Head every head role heads -
190619 190226 NAACL 2019 Attention not explanation weighted correction + robust AttentionExplanation -

Tabular Learning

Read Public Conference Title HighLight Code Other
191006 190926 - TabNet NN method googleResearch interpretable

Unbalance Classify

Read Public Conference Title HighLight Code Other
191111 191107 - Dice Loss in NLP like F1 FP==FN - -
191011 190116 ICLR 2019 Class-Balance Loss effective number sample googleResearch -

Learning With Noisy Labels

Read Public Conference Title HighLight Code Other
191029 181030 NIPS 2018 Co-teaching Memorize effect Co-teaching -

Multi-task

Read Public Conference Title HighLight Code Other
191216 170214 ECCV 2016 Learning without forgetting Multi-task by no old data LwF -

Dropout

Read Public Conference Title HighLight Code Other
191228 190926 ICLR 2020 Mixout origin + dropout - -

Demo

Read Public Conference Title HighLight Code Other
191218 191015 [ICMLA 2019] ComprehendMedical Medical NER + RE API AWS -
191011 191009 - Transformers Unified API Transformers -

CV

Video Prediction

Read Public Conference Title HighLight Code Other
191005 190926 ICLR 2020 CrevNet information preserving - -

License

Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)

Copyright (c) 2019-present, gunjianpan(iofu728)